Search Results for author:
Found 165 papers, 48 papers with code
DanceChat: Large Language Model-Guided Music-to-Dance Generation
This approach goes beyond implicit learning from music alone, enabling the model to generate dance that is both more diverse and better aligned with musical styles.
Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems
Joint-GCG's innovative unification of gradient-based attacks across retrieval and generation stages fundamentally reshapes our understanding of vulnerabilities within RAG systems.
Towards Robust Overlapping Speech Detection: A Speaker-Aware Progressive Approach Using WavLM
Overlapping Speech Detection (OSD) aims to identify regions where multiple speakers overlap in a conversation, a critical challenge in multi-party speech processing.
Towards a More Generalized Approach in Open Relation Extraction
In this paper, we propose a generalized OpenRE setting that considers unlabeled data as a mixture of both known and novel instances.
AdInject: Real-World Black-Box Attacks on Web Agents via Advertising Delivery
In this paper, we propose AdInject, a novel and real-world black-box attack method that leverages the internet advertising delivery to inject malicious content into the Web Agent's environment.
Multi-Domain Audio Question Answering Toward Acoustic Content Reasoning in The DCASE 2025 Challenge
We present Task 5 of the DCASE 2025 Challenge: an Audio Question Answering (AQA) benchmark spanning multiple domains of sound understanding.
scDrugMap: Benchmarking Large Foundation Models for Drug Response Prediction
In the pooled-data scenario, scFoundation achieved the best performance, with mean F1 scores of 0. 971 (layer freezing) and 0. 947 (fine-tuning), outperforming the lowest-performing model by over 50%.
LODAP: On-Device Incremental Learning Via Lightweight Operations and Data Pruning
During incremental learning, EIM exploits some lightweight operations, called adapters, to effectively and efficiently learn features for new classes so that it can improve the accuracy of incremental learning while reducing model complexity as well as training overhead.
Improving Significant Wave Height Prediction Using Chronos Models
Accurate wave height prediction is critical for maritime safety and coastal resilience, yet conventional physics-based models and traditional machine learning methods face challenges in computational efficiency and nonlinear dynamics modeling.
The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report
This paper presents a comprehensive review of the NTIRE 2025 Challenge on Single-Image Efficient Super-Resolution (ESR).
NTR-Gaussian: Nighttime Dynamic Thermal Reconstruction with 4D Gaussian Splatting Based on Thermodynamics
Thermal infrared imaging offers the advantage of all-weather capability, enabling non-intrusive measurement of an object's surface temperature.
PhenoProfiler: Advancing Phenotypic Learning for Image-based Drug Discovery
PhenoProfiler is designed as an end-to-end tool that processes whole-slide multi-channel images directly into low-dimensional quantitative representations, eliminating the extensive computational steps required by existing methods.
Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System
Inspired by the concept of mimicking the familiar, AutoCMD is capable of inferring the information utilized by upstream tools in the toolchain through learning on open-source systems and reinforcement with target system examples, thereby generating more targeted commands for information theft.
Divergence-Augmented Policy Optimization
In deep reinforcement learning, policy optimization methods need to deal with issues such as function approximation and the reuse of off-policy data.
An Experimental Study on Joint Modeling for Sound Event Localization and Detection with Source Distance Estimation
In traditional sound event localization and detection (SELD) tasks, the focus is typically on sound event detection (SED) and direction-of-arrival (DOA) estimation, but they fall short of providing full spatial information about the sound source.
Understanding Individual Agent Importance in Multi-Agent System via Counterfactual Reasoning
Inspired by counterfactual reasoning, a larger change in reward caused by the randomized action of agent indicates its higher importance.
What External Knowledge is Preferred by LLMs? Characterizing and Exploring Chain of Evidence in Imperfect Context
Incorporating external knowledge into large language models (LLMs) has emerged as a promising approach to mitigate outdated knowledge and hallucination in LLMs.
DeepSN: A Sheaf Neural Framework for Influence Maximization
They have developed methods to learn the underlying diffusion processes in a data-driven manner, which enhances the generalizability of the solution, and have designed optimization objectives to identify the optimal seed set.
Asymmetric Learning for Spectral Graph Neural Networks
Extensive experiments on eighteen benchmark datasets show that asymmetric learning consistently improves the performance of spectral GNNs for both heterophilic and homophilic graphs.
From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection
To fill this gap, we present ToolCommander, a novel framework designed to exploit vulnerabilities in LLM tool-calling systems through adversarial tool injection.
Style3D: Attention-guided Multi-view Style Transfer for 3D Object Generation
Specifically, the query features from the content image preserve geometric consistency across multiple views, while the key and value features from the style image are used to guide the stylistic transfer.
User-Movement-Robust Virtual Reality Through Dual-Beam Reception in mmWave Networks
Evaluation using actual HMD movement data demonstrates the effectiveness of our approach, showcasing a reduction in outage rates of up to 13% compared to quasi-omnidirectional reception with two serving APs, and a 17% decrease compared to steerable single-beam reception with a serving AP.
Material Anything: Generating Materials for Any 3D Object via Diffusion
We present Material Anything, a fully-automated, unified diffusion framework designed to generate physically-based materials for 3D objects.
CoNFiLD-inlet: Synthetic Turbulence Inflow Using Generative Latent Diffusion Models with Neural Fields
Eddy-resolving turbulence simulations require stochastic inflow conditions that accurately replicate the complex, multi-scale structures of turbulence.
MVANet: Multi-Stage Video Attention Network for Sound Event Localization and Detection with Source Distance Estimation
We propose a novel output representation that combines the DOA with distance of sound sources by calculating the real Cartesian coordinates to address the newly introduced source distance estimation (SDE) task in the Detection and Classification of Acoustic Scenes and Events (DCASE) 2024 Challenge.
Bridge: A Unified Framework to Knowledge Graph Completion via Language Models and Knowledge Representation
Furthermore, to bridge the gap between KGs and PLMs, we employ a self-supervised representation learning method called BYOL to fine-tune PLMs with two different views of a triple.
STEM-POM: Evaluating Language Models Math-Symbol Reasoning in Document Parsing
Advances in large language models (LLMs) have spurred research into enhancing their reasoning capabilities, particularly in math-rich STEM documents.
CodePurify: Defend Backdoor Attacks on Neural Code Models via Entropy-based Purification
In this study, we propose CodePurify, a novel defense against backdoor attacks on code models through entropy-based purification.
Learning Partial Graph Matching via Optimal Partial Transport
While recent studies have explored deep learning techniques for partial graph matching, a significant limitation remains: the absence of an optimization objective that fully captures the problem's intrinsic nature while enabling efficient solutions.
Diverse Policies Recovering via Pointwise Mutual Information Weighted Imitation Learning
Recovering a spectrum of diverse policies from a set of expert trajectories is an important research topic in imitation learning.
Towards Bridging Generalization and Expressivity of Graph Neural Networks
Expressivity and generalization are two critical aspects of graph neural networks (GNNs).
The USTC-NERCSLIP Systems for the CHiME-8 MMCSG Challenge
In the two-person conversation scenario with one wearing smart glasses, transcribing and displaying the speaker's content in real-time is an intriguing application, providing a priori information for subsequent tasks such as translation and comprehension.
From Prohibition to Adoption: How Hong Kong Universities Are Navigating ChatGPT in Academic Workflows
This paper aims at comparing the time when Hong Kong universities used to ban ChatGPT to the current periods where it has become integrated in the academic processes.
See then Tell: Enhancing Key Information Extraction with Vision Grounding
Positioned at the outset of the answer text, the <see> token allows the model to first see--observing the regions of the image related to the input question--and then tell--providing articulated textual responses.
Investigating Context-Faithfulness in Large Language Models: The Roles of Memory Strength and Evidence Style
In this study, we investigate the impact of memory strength and evidence presentation on LLMs' receptiveness to external evidence.
Rational-WENO: A lightweight, physically-consistent three-point weighted essentially non-oscillatory scheme
Conventional WENO3 methods are known to be highly dissipative at lower resolutions, introducing significant errors in the pre-asymptotic regime.
NPU-NTU System for Voice Privacy 2024 Challenge
Our system employs a disentangled neural codec architecture and a serial disentanglement strategy to gradually disentangle the global speaker identity and time-variant linguistic content and paralinguistic information.
BFA-YOLO: A balanced multiscale object detection network for building façade attachments detection
To address these issues, we develop the BFA-YOLO model and the BFA-3D dataset in this study.
PatUntrack: Automated Generating Patch Examples for Issue Reports without Tracked Insecure Code
In such cases, providing examples of insecure code and the corresponding patches would benefit the security developers to better locate and fix the insecure code.
MUSA: Multi-lingual Speaker Anonymization via Serial Disentanglement
Meanwhile, we propose a straightforward anonymization strategy that employs empty embedding with zero values to simulate the speaker identity concealment process, eliminating the need for conversion to a pseudo-speaker identity and thereby reducing the complexity of speaker anonymization process.
Enhancing Terrestrial Net Primary Productivity Estimation with EXP-CASA: A Novel Light Use Efficiency Model Approach
The EXP-CASA model effectively improves the CASA model by using novel functions for estimating the fraction of absorbed photosynthetically active radiation (FPAR) and environmental stress, by utilizing long-term observational data from FLUXNET and MODIS surface reflectance data.
Repairing Catastrophic-Neglect in Text-to-Image Diffusion Models via Attention-Guided Feature Enhancement
The most prominent issue among these semantic inconsistencies is catastrophic-neglect, where the images generated by T2I DMs miss key objects mentioned in the prompt.
Exploring Audio-Visual Information Fusion for Sound Event Localization and Detection In Low-Resource Realistic Scenarios
Evaluation results on the Detection and Classification of Acoustic Scenes and Events (DCASE) 2023 Challenge data set demonstrate significant improvements in SELD performances.
SRFUND: A Multi-Granularity Hierarchical Structure Reconstruction Benchmark in Form Understanding
Accurately identifying and organizing textual content is crucial for the automation of document processing in the field of form understanding.
A Variance-Preserving Interpolation Approach for Diffusion Models with Applications to Single Channel Speech Enhancement and Recognition
In this paper, we propose a variance-preserving interpolation framework to improve diffusion models for single-channel speech enhancement (SE) and automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Distinctive and Natural Speaker Anonymization via Singular Value Transformation-assisted Matrix
To address these issues and especially generate more natural and distinctive anonymized speech, we propose a novel speaker anonymization approach that models a matrix related to speaker identity and transforms it into an anonymized singular value transformation-assisted matrix to conceal the original speaker identity.
The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report
In sub-track 1, the practical runtime performance of the submissions was evaluated, and the corresponding score was used to determine the ranking.
Generalization of Graph Neural Networks through the Lens of Homomorphism
In this work, we propose to study the generalization of GNNs through a novel perspective - analyzing the entropy of graph homomorphism.
Local Vertex Colouring Graph Neural Networks
Specifically, we propose a new vertex colouring scheme and demonstrate that classical search algorithms can efficiently compute graph representations that extend beyond the 1-WL.
VEglue: Testing Visual Entailment Systems via Object-Aligned Joint Erasing
Visual entailment (VE) is a multimodal reasoning task consisting of image-sentence pairs whereby a promise is defined by an image, and a hypothesis is described by a sentence.
Adversarial Testing for Visual Grounding via Image-Aware Property Reduction
To this end, we propose PEELING, a text perturbation approach via image-aware property reduction for adversarial testing of the VG model.
Re-Examine Distantly Supervised NER: A New Benchmark and a Simple Approach
We found that many of them rely on large validation sets and some used test set for tuning inappropriately.
Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues
With the development of LLMs, the security threats of LLMs are getting more and more attention.
SNP-S3: Shared Network Pre-training and Significant Semantic Strengthening for Various Video-Text Tasks
By employing one shared BERT-type network to refine textual and cross-modal features simultaneously, SNP is lightweight and could support various downstream applications.
Dual-View Data Hallucination with Semantic Relation Guidance for Few-Shot Image Recognition
Specifically, an instance-view data hallucination module hallucinates each sample of a novel class to generate new data by employing local semantic correlated attention and global semantic feature fusion derived from base classes.
Uplifting the Expressive Power of Graph Neural Networks through Graph Partitioning
In this work, we study the expressive power of graph neural networks through the lens of graph partitioning.
Large Language Models are Complex Table Parsers
With the Generative Pre-trained Transformer 3. 5 (GPT-3. 5) exhibiting remarkable reasoning and comprehension abilities in Natural Language Processing (NLP), most Question Answering (QA) research has primarily centered around general QA tasks based on GPT, neglecting the specific challenges posed by Complex Table QA.
Joint Training or Not: An Exploration of Pre-trained Speech Models in Audio-Visual Speaker Diarization
The scarcity of labeled audio-visual datasets is a constraint for training superior audio-visual speaker diarization systems.
Improving Unsupervised Relation Extraction by Augmenting Diverse Sentence Pairs
We also identify the limitation of noise-contrastive estimation (NCE) loss for relation representation learning and propose to apply margin loss for sentence pairs.
CoRec: An Easy Approach for Coordination Recognition
In this paper, we observe and address the challenges of the coordination recognition task.
HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generation
The main idea is to enhance the model's 2D perception of 3D geometry by learning a normal-adapted diffusion model and a normal-aligned diffusion model.
PP-MeT: a Real-world Personalized Prompt based Meeting Transcription System
Speaker-attributed automatic speech recognition (SA-ASR) improves the accuracy and applicability of multi-speaker ASR systems in real-world scenarios by assigning speaker labels to transcribed texts.
MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo
We design a multi-scale windows PatchMatch (mPM) to obtain reliable depth of untextured areas.
Learning Segment Similarity and Alignment in Large-Scale Content Based Video Retrieval
SSAN is based on two newly proposed modules in video retrieval: (1) An efficient Self-supervised Keyframe Extraction (SKE) module to reduce redundant frame features, (2) A robust Similarity Pattern Detection (SPD) module for temporal alignment.
Dual-Modal Attention-Enhanced Text-Video Retrieval with Triplet Partial Margin Contrastive Learning
We thereby present a new Triplet Partial Margin Contrastive Learning (TPM-CL) module to construct partial order triplet samples by automatically generating fine-grained hard negatives for matched text-video pairs.
Ranked #4 on
Video Retrieval
on MSR-VTT-1kA
Hierarchical Audio-Visual Information Fusion with Multi-label Joint Decoding for MER 2023
Three different structures based on attention-guided feature gathering (AFG) are designed for deep feature fusion.
How to Evaluate the Generalization of Detection? A Benchmark for Comprehensive Open-Vocabulary Detection
Extensive experimental results show that existing top OVD models all fail on the new tasks except for simple object types, demonstrating the value of the proposed dataset in pinpointing the weakness of current OVD models and guiding future research.
Ranked #1 on
Negation
on OVDEval
Federated Reinforcement Learning for Electric Vehicles Charging Control on Distribution Networks
To effectively learn the optimal EV charging control strategy, a federated deep reinforcement learning algorithm named FedSAC is further proposed.
Inverting the Imaging Process by Learning an Implicit Camera Model
In principle, our new implicit neural camera model has the potential to benefit a wide array of other inverse imaging tasks.
Local Implicit Ray Function for Generalizable Radiance Field Representation
To solve this problem, we propose LIRF to aggregate the information from conical frustums to construct a ray.
Multi-agent Policy Reciprocity with Theoretical Guarantee
We then define an adjacency space for mismatched states and design a plug-and-play module for value iteration, which enables agents to infer more precise returns.
N-WL: A New Hierarchy of Expressivity for Graph Neural Networks
The expressive power of Graph Neural Networks (GNNs) is fundamental for understanding their capabilities and limitations, i. e., what graph properties can or cannot be learnt by a GNN.
Wide-Angle Rectification via Content-Aware Conformal Mapping
Despite the proliferation of ultra wide-angle lenses on smartphone cameras, such lenses often come with severe image distortion (e. g. curved linear structure, unnaturally skewed faces).
CNVid-3.5M: Build, Filter, and Pre-Train the Large-Scale Public Chinese Video-Text Dataset
Though there are certain methods studying the Chinese video-text pre-training, they pre-train their models on private datasets whose videos and text are unavailable.
A Unified Object Counting Network with Object Occupation Prior
In this paper, we build the first evolving object counting dataset and propose a unified object counting network as the first attempt to address this task.
Performance Evaluation, Optimization and Dynamic Decision in Blockchain Systems: A Recent Overview
We believe that the basic theory with mathematical methods, algorithms and simulations of blockchain systems discussed in this paper will strongly support future development and continuous innovation of blockchain technology.
A SVD-based Dynamic Harmonic Phasor Estimator with Improved Suppression of Out-of-Band Interference
The diffusion of nonlinear loads and power electronic devices in power systems deteriorates the signal environment and increases the difficulty of measuring harmonic phasors.
Preserving background sound in noise-robust voice conversion via multi-task learning
Background sound is an informative form of art that is helpful in providing a more immersive experience in real-application voice conversion (VC) scenarios.
Distinguishable Speaker Anonymization based on Formant and Fundamental Frequency Scaling
By directly scaling the formant and F0, the speaker distinguishability degradation of the anonymized speech caused by the introduction of other speakers is prevented.
TSUP Speaker Diarization System for Conversational Short-phrase Speaker Diarization Challenge
In this challenge, we explore three kinds of typical speaker diarization systems, which are spectral clustering(SC) based diarization, target-speaker voice activity detection(TS-VAD) and end-to-end neural diarization(EEND) respectively.
Deep Learning Based Audio-Visual Multi-Speaker DOA Estimation Using Permutation-Free Loss Function
In this paper, we propose a deep learning based multi-speaker direction of arrival (DOA) estimation with audio and visual signals by using permutation-free loss function.
NWPU-ASLP System for the VoicePrivacy 2022 Challenge
Our system consists of four modules, including feature extractor, acoustic model, anonymization module, and neural vocoder.
On the Convergence Theory of Meta Reinforcement Learning with Personalized Policies
Modern meta-reinforcement learning (Meta-RL) methods are mainly developed based on model-agnostic meta-learning, which performs policy gradient steps across tasks to maximize policy performance.
Automatic Comment Generation via Multi-Pass Deliberation
Then, we treat the comment of the retrieved code as the initial draft and input it with the code and keywords into DECOM to start the iterative deliberation process.
Tensor Decomposition based Personalized Federated Learning
Federated learning (FL) is a new distributed machine learning framework that can achieve reliably collaborative training without collecting users' private data.
DBE-KT22: A Knowledge Tracing Dataset Based on Online Student Evaluation
This is known as the \emph{Knowledge Tracing} problem in the literature.
Restructuring Graph for Higher Homophily via Adaptive Spectral Clustering
While a growing body of literature has been studying new Graph Neural Networks (GNNs) that work on both homophilic and heterophilic graphs, little has been done on adapting classical GNNs to less-homophilic graphs.
Ranked #34 on
Node Classification
on Squirrel
NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Results
This challenge includes three tracks.
Stereo Unstructured Magnification: Multiple Homography Image for View Synthesis
A two-stage network is developed for novel view synthesis.
Epipolar Focus Spectrum: A Novel Light Field Representation and Application in Dense-view Reconstruction
Existing light field representations, such as epipolar plane image (EPI) and sub-aperture images, do not consider the structural characteristics across the views, so they usually require additional disparity and spatial structure cues for follow-up tasks.
CardioID: Mitigating the Effects of Irregular Cardiac Signals for Biometric Identification
In this work, we analyze cardiac signals collected in more realistic (uncontrolled) scenarios and show that their high signal variability (i. e., irregularity) makes it harder to obtain stable and distinct user features.
Sparse Federated Learning with Hierarchical Personalized Models
To this end, we propose a personalized FL algorithm using a hierarchical proximal mapping based on the moreau envelop, named sparse federated learning with hierarchical personalized models (sFedHP), which significantly improves the global model performance facing diverse data.
MatchFormer: Interleaving Attention in Transformers for Feature Matching
While detector-based methods coupled with feature descriptors struggle in low-texture scenes, CNN-based methods with a sequential extract-to-match pipeline, fail to make use of the matching capacity of the encoder and tend to overburden the decoder for matching.
A study on joint modeling and data augmentation of multi-modalities for audio-visual scene classification
In this paper, we propose two techniques, namely joint modeling and data augmentation, to improve system performances for audio-visual scene classification (AVSC).
A Large-scale Comprehensive Dataset and Copy-overlap Aware Evaluation Protocol for Segment-level Video Copy Detection
In this paper, we introduce VCSL (Video Copy Segment Localization), a new comprehensive segment-level annotated video copy dataset.
GUDN: A novel guide network with label reinforcement strategy for extreme multi-label text classification
Large-scale pre-trained models have brought a new trend to this problem.
Knowledge Tracing: A Survey
A human teacher can track the knowledge of students to customize the teaching on students needs.
Fast and Unsupervised Action Boundary Detection for Action Segmentation
To deal with the great number of untrimmed videos produced every day, we propose an efficient unsupervised action segmentation method by detecting boundaries, named action boundary detection (ABD).
Deep Open Set Identification for RF Devices
Artificial intelligence (AI) based device identification improves the security of the internet of things (IoT), and accelerates the authentication process.
SIDNet: Learning Shading-aware Illumination Descriptor for Image Harmonization
Before solving these two sub-problems, we first learn a shading-aware illumination descriptor via a well-designed neural rendering framework, of which the key is a shading bases module that generates multiple shading bases from the foreground image.
HDR-NeRF: High Dynamic Range Neural Radiance Fields
The key to our method is to model the physical imaging process, which dictates that the radiance of a scene point transforms to a pixel value in the LDR image with two implicit functions: a radiance field and a tone mapper.
Ranked #2 on
Novel View Synthesis
on HDR-GS
Learning Data Teaching Strategies Via Knowledge Tracing
In this paper, we propose a novel method, called Knowledge Augmented Data Teaching (KADT), which can optimize a data teaching strategy for a student model by tracing its knowledge progress over multiple learning concepts in a learning task.
A Regularized Wasserstein Framework for Graph Kernels
This framework provides a novel optimal transport distance metric, namely Regularized Wasserstein (RW) discrepancy, which can preserve both features and structure of graphs via Wasserstein distances on features and their local variations, local barycenters and global connectivity.
A New Perspective on "How Graph Neural Networks Go Beyond Weisfeiler-Lehman?"
To elaborate this framework, we propose a novel neural model, called GraphSNN, and prove that this model is strictly more expressive than the Weisfeiler Lehman test in distinguishing graph structures.
Multiple Intelligent Reflecting Surface aided Multi-user Weighted Sum-Rate Maximization using Manifold Optimization
Intelligent reflecting surface (IRS) are able to amend radio propagation condition tasks on account of its functional properties in phase shift optimizing.
Deep Graph Memory Networks for Forgetting-Robust Knowledge Tracing
Further, this model has the capability of learning relationships between latent concepts from a dynamic latent concept graph in light of a student's evolving knowledge states.
VTLayout: Fusion of Visual and Text Features for Document Layout Analysis
In the second stage, the deep visual, shallow visual, and text features are extracted for fusion to identify the category blocks of documents.
Structured Directional Pruning via Perturbation Orthogonal Projection
Structured pruning is an effective compression technique to reduce the computation of neural networks, which is usually achieved by adding perturbations to reduce network parameters at the cost of slightly increasing training loss.
Sparse Personalized Federated Learning
By incorporating an approximated L1-norm and the correlation between client models and global model into standard FL loss function, the performance on statistical diversity data is improved and the communicational and computational loads required in the network are reduced compared with non-sparse FL.
A Lottery Ticket Hypothesis Framework for Low-Complexity Device-Robust Neural Acoustic Scene Classification
We propose a novel neural model compression strategy combining data augmentation, knowledge transfer, pruning, and quantization for device-robust acoustic scene classification (ASC).
The Use of Bandit Algorithms in Intelligent Interactive Recommender Systems
In today's business marketplace, many high-tech Internet enterprises constantly explore innovative ways to provide optimal online user experiences for gaining competitive advantages.
Episode Adaptive Embedding Networks for Few-shot Learning
Few-shot learning aims to learn a classifier using a few labelled instances for each class.
Pose2Drone: A Skeleton-Pose-based Framework for Human-Drone Interaction
Our framework provides the functionality to control the movement of the drone with simple arm gestures and to follow the user while keeping a safe distance.
Explore BiLSTM-CRF-Based Models for Open Relation Extraction
Extracting multiple relations from text sentences is still a challenge for current Open Relation Extraction (Open RE) tasks.
NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results
This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with a focus on the proposed methods and results.
Beyond Low-Pass Filters: Adaptive Feature Propagation on Graphs
The proposed model is shown to generalize well to both homophilic and heterophilic graphs.
Multi-Scale Feature Pyramid Network: A Heavily Occluded Pedestrian Detection Network Based on ResNet
MFPN includes two modules, namely double feature pyramid network (FPN) integrated with ResNet (DFR) and repulsion loss of minimum (RLM).
The NPU System for the 2020 Personalized Voice Trigger Challenge
This paper describes the system developed by the NPU team for the 2020 personalized voice trigger challenge.
FIXME: Enhance Software Reliability with Hybrid Approaches in Cloud
The process of continuous integration/deployment (CICD) in cloud connects developers who need to deliver value faster and more transparently with site reliability engineers (SREs) who need to manage applications reliably.
Machine learning accelerated computational fluid dynamics
Numerical simulation of fluids plays an essential role in modeling many physical phenomena, such as weather, climate, aerodynamics and plasma physics.
Deep Anti-aliasing of Whole Focal Stack Using Slice Spectrum
Based on these two observations, we propose a learning-based FSS reconstruction approach for one-time aliasing removing over the whole focal stack.
Chiral effective Lagrangian for excited heavy-light mesons from QCD
We derive the chiral effective Lagrangian for excited heavy-light mesons from QCD under proper approximations.
High Energy Physics - Phenomenology
Global Node Attentions via Adaptive Spectral Filters
The proposed model has been shown to generalize well to both assortative and disassortative graphs.
ErGAN: Generative Adversarial Networks for Entity Resolution
Entity resolution targets at identifying records that represent the same real-world entity from one or more datasets.
Chiral effective Lagrangian for heavy-light mesons from QCD: $1/m_{Q}$ correction
The low energy constants in the effective Lagrangian are expressed in terms of the light quark self-energy and heavy quark mass $m_Q$.
High Energy Physics - Phenomenology
Emotion Classification by Jointly Learning to Lexiconize and Classify
Emotion lexicons have been shown effective for emotion classification (Baziotis et al., 2018).
Lightweight Single-Image Super-Resolution Network with Attentive Auxiliary Feature Learning
In this paper, we develop a computation efficient yet accurate network based on the proposed attentive auxiliary features (A$^2$F) for SISR.
Frequency Gating: Improved Convolutional Neural Networks for Speech Enhancement in the Time-Frequency Domain
One of the strengths of traditional convolutional neural networks (CNNs) is their inherent translational invariance.
Deep Learning Models for Predicting Wildfires from Historical Remote-Sensing Data
Identifying regions that have high likelihood for wildfires is a key component of land and forestry management and disaster preparedness.
AIM 2020: Scene Relighting and Illumination Estimation Challenge
The first track considered one-to-one relighting; the objective was to relight an input photo of a scene with a different color temperature and illuminant orientation (i. e., light source position).
PEL-BERT: A Joint Model for Protocol Entity Linking
Pre-trained models such as BERT are widely used in NLP tasks and are fine-tuned to improve the performance of various NLP tasks consistently.
Knowledge Tracing with Sequential Key-Value Memory Networks
Although these deep learning models have shown promising results, they have limitations: either lack the ability to go deeper to trace how specific concepts in a knowledge state are mastered by a student, or fail to capture long-term dependencies in an exercise sequence.
DFNets: Spectral CNNs for Graphs with Feedback-Looped Filters
We propose a novel spectral convolutional neural network (CNN) model on graph structured data, namely Distributed Feedback-Looped Networks (DFNets).
Ranked #1 on
Node Classification
on NELL
Signal Instructed Coordination in Cooperative Multi-agent Reinforcement Learning
Although existing works formulate this problem into a centralized learning with decentralized execution framework, which avoids the non-stationary problem in training, their decentralized execution paradigm limits the agents' capability to coordinate.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
Learning to Sample: an Active Learning Framework
However, current learning-based active learning approaches still require sufficient training data so as to generalize meta-learning models for active learning.
Arena: a toolkit for Multi-Agent Reinforcement Learning
We introduce Arena, a toolkit for multi-agent reinforcement learning (MARL) research.
Contextualized Spatial-Temporal Network for Taxi Origin-Destination Demand Prediction
Finally, a GCC module is applied to model the correlation between all regions by computing a global correlation feature as a weighted sum of all regional features, with the weights being calculated as the similarity between the corresponding region pairs.
Semantic Relationships Guided Representation Learning for Facial Action Unit Recognition
Specifically, by analyzing the symbiosis and mutual exclusion of AUs in various facial expressions, we organize the facial AUs in the form of structured knowledge-graph and integrate a Gated Graph Neural Network (GGNN) in a multi-scale CNN framework to propagate node information through the graph for generating enhanced AU representation.
I4U Submission to NIST SRE 2018: Leveraging from a Decade of Shared Experiences
The I4U consortium was established to facilitate a joint entry to NIST speaker recognition evaluations (SRE).
Robust Visual Tracking Using Dynamic Classifier Selection with Sparse Representation of Label Noise
However, the self-updating scheme makes these methods suffer from drifting problem because of the incorrect labels of weak classifiers in training samples.
Breaking the Spatio-Angular Trade-off for Light Field Super-Resolution via LSTM Modelling on Epipolar Plane Images
We prove that the light field is a 2D series, thus, a specifically designed CNN-LSTM network is proposed to capture the continuity property of the EPI.
Facial Landmark Machines: A Backbone-Branches Architecture with Progressive Representation Learning
In this paper, we propose a novel cascaded backbone-branches fully convolutional neural network~(BB-FCN) for rapidly and accurately localizing facial landmarks in unconstrained and cluttered settings.
Exponentially Weighted Imitation Learning for Batched Historical Data
We consider deep policy learning with only batched historical trajectories.
Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action Space
Most existing deep reinforcement learning (DRL) frameworks consider either discrete action space or continuous action space solely.
TStarBots: Defeating the Cheating Level Builtin AI in StarCraft II in the Full Game
Both TStarBot1 and TStarBot2 are able to defeat the built-in AI agents from level 1 to level 10 in a full game (1v1 Zerg-vs-Zerg game on the AbyssalReef map), noting that level 8, level 9, and level 10 are cheating agents with unfair advantages such as full vision on the whole map and resource harvest boosting.
A Generic Multi-Projection-Center Model and Calibration Method for Light Field Cameras
Based on the MPC model and projective transformation, we propose a calibration algorithm to verify our light field camera model.
Dense Light Field Reconstruction From Sparse Sampling Using Residual Network
A light field records numerous light rays from a real-world scene.
End-to-end driving simulation via angle branched network
Imitation learning for end-to-end autonomous driving has drawn attention from academic communities.
NeuroStorm: Accelerating Brain Science Discovery in the Cloud
Neuroscientists are now able to acquire data at staggering rates across spatiotemporal scales.
PARAMETRIZED DEEP Q-NETWORKS LEARNING: PLAYING ONLINE BATTLE ARENA WITH DISCRETE-CONTINUOUS HYBRID ACTION SPACE
Most existing deep reinforcement learning (DRL) frameworks consider action spaces that are either discrete or continuous space.
Light Field Segmentation From Super-pixel Graph Representation
The large volume of input data and the redundancy of light field make it an open challenge.
MTNA: A Neural Multi-task Model for Aspect Category Classification and Aspect Term Extraction On Restaurant Reviews
Online reviews are valuable resources not only for consumers to make decisions before purchase, but also for providers to get feedbacks for their services or commodities.
Online Interactive Collaborative Filtering Using Multi-Armed Bandit with Dependent Arms
To address these issues, collaborative filtering (CF), one of the recommendation techniques relying on the interaction data only, as well as the online multi-armed bandit mechanisms, capable of achieving the balance between exploitation and exploration, are adopted in the online interactive recommendation settings, by assuming independent items (i. e., arms).
4D Light Field Superpixel and Segmentation
Superpixel segmentation of 2D image has been widely used in many computer vision tasks.
Collective Vertex Classification Using Recursive Neural Network
In this paper, we propose a graph-based recursive neural network framework for collective vertex classification.
Towards Evidence-Based Ontology for Supporting Systematic Literature Review
[Conclusions]: The approach of using ontology could effectively and efficiently support the conducting of systematic literature review.
Discovering and Deciphering Relationships Across Disparate Data Modalities
Understanding the relationships between different properties of data, such as whether a connectome or genome has information about disease status, is becoming increasingly important in modern biological datasets.
Unconstrained Two-parallel-plane Model for Focused Plenoptic Cameras Calibration
The geometry of the recovered scene structure is affected by the calibration of the plenoptic camera significantly.
Occlusion-Model Guided Anti-Occlusion Depth Estimation in Light Field
Occlusion is one of the most challenging problems in depth estimation.
DARI: Distance metric And Representation Integration for Person Verification
The past decade has witnessed the rapid development of feature representation learning and distance metric learning, whereas the two steps are often discussed separately.
Ranked #7 on
Person Re-Identification
on SYSU-30k
(using extra training data)
Data-Driven Scene Understanding with Adaptively Retrieved Exemplars
In the first step, the references are selected by jointly matching their appearances with the target as well as the semantics (i. e. the assigned labels of the target and the references).
Aliasing Detection and Reduction in Plenoptic Imaging
When using plenoptic camera for digital refocusing, angular undersampling can cause severe (angular) aliasing artifacts.
